i-2-7

Documents about i-2-7

• Pretrained Persona Mixture Models and Tandem Models for Human Simulation#1037290arXiv (All)
• Representation of syntax in LLMs through the lens of linear distance and similarity-aware entropy#779728arXiv (OAI Expanded)
• Representation of syntax in LLMs through the lens of linear distance and similarity-aware entropy#781103arXiv (All)
• Multimodal Resource-Exhaustion Attacks on Vision-Language Models via Joint Pixel-Prompt Optimization#973509arXiv (All)
• 7 U.S.C. § 1446f — Repealed. Pub. L. 104–127, title I, § 171(b)(2)(H), Apr. 4, 1996, 110 Stat. 938#561721US Code (LII)
• 7 U.S.C. § 1444f — Repealed. Pub. L. 104–127, title I, § 171(b)(2)(C), Apr. 4, 1996, 110 Stat. 938#561742US Code (LII)
• 7 U.S.C. § 1445h — Repealed. Pub. L. 104–127, title I, § 171(b)(2)(F), Apr. 4, 1996, 110 Stat. 938#561760US Code (LII)
• Where the Verifier Fails: A Category-Level Audit of Reward Signals in RLVR#821295arXiv (All)
• RCL: A Retrieval-Confidence Layer for Detecting Insufficient Context in Enterprise Retrieval-Augmented Code Generation#998591arXiv (All)
• Evaluating Multimodal LLMs across Text and Audio Modalities for Accessible Disaster Assistance#609088arXiv (OAI Expanded)
• LayerRoute: Input-Conditioned Adaptive Layer Skipping via LoRA Fine-Tuning for Agentic Language Models#974446arXiv (All)
• pykci: A Compact Urban Knowledge Graph for Semantic and Spatial Queries using LLMs#986289arXiv (All)
• BaltiVoice: A Speech Corpus and Fine-tuned Whisper ASR System for the Balti Language#987696arXiv (All)
• From Architecture to Output: Structural Origins of Hallucination in Large Language Models and the Amplifying Role of Data#971818arXiv (All)
• More Context, Larger Models, or Moral Knowledge? A Systematic Study of Schwartz Value Detection in Political Texts#984162arXiv (All)
• 7 U.S.C. § 1444f-1 — Repealed. Pub. L. 102–237, title I, § 114(b)(2), Dec. 13, 1991, 105 Stat. 1840#561743US Code (LII)
• Excess Separability: Nuisance-Controlled Residual-Stream Probing for Benchmark Contamination Detection#614236arXiv (OAI Expanded)
• Excess Separability: Nuisance-Controlled Residual-Stream Probing for Benchmark Contamination Detection#615203arXiv (All)
• Memory Efficient Audio Synthesis with Decoupled Temporal Depth Diffusion Transformers#618709arXiv (OAI Expanded)
• Memory Efficient Audio Synthesis with Decoupled Temporal Depth Diffusion Transformers#620388arXiv (All)
• Mitigating Identity Essentialism in LLM Agents with Longitudinal Life Trajectories#656772arXiv (OAI Expanded)
• Mitigating Identity Essentialism in LLM Agents with Longitudinal Life Trajectories#658908arXiv (All)
• Comprehensiveness Metrics for Automatic Evaluation of Factual Recall in Text Generation#797245arXiv (OAI Expanded)
• Comprehensiveness Metrics for Automatic Evaluation of Factual Recall in Text Generation#798659arXiv (All)
• Annotated Surrogate Retrieval for Polish Statutory Law#808971arXiv (OAI Expanded)
• Annotated Surrogate Retrieval for Polish Statutory Law#818963arXiv (All)
• TRACE: Trajectory Correction from Cross-layer Evidence for Hallucination Reduction#973177arXiv (All)
• Retrieval-Augmented Multi-Prompt Ensemble for Minor-Grain Breeding Information Extraction#975192arXiv (All)
• Osprey: Target-agnostic Pre-training Makes Stronger Drafters in Speculative Decoding#987097arXiv (All)
• EviGen: Predictive Evidence Scaffolding for Verifiable Clinical Rationale Generation#1013010arXiv (All)
• The Complexity Kink: A Prompt-Side Structural Complexity Index for Code-Generation Reliability#1014206arXiv (All)
• Auditing Bias and Safety in Voice AI Customer Care#927509arXiv (All)
• A Version Space Approach for Digital Circuit Analysis#820036arXiv (All)
• Hierarchical attention interpretation: an interpretable speech-level transformer for bi-modal depression detection#1035253arXiv (All)
• MultiFinRAG: An Optimized Multimodal Retrieval-Augmented Generation (RAG) Framework for Financial Question Answering#131347arXiv (OAI)
• A Unified Conditional Flow for Motion Generation, Editing, and Intra-Structural Retargeting#674369arXiv (OAI Expanded)
• A Unified Conditional Flow for Motion Generation, Editing, and Intra-Structural Retargeting#677568arXiv (All)
• Multirate State Space Models for End-to-End Processing of Pulse Density Modulated Speech Signals#788475arXiv (OAI Expanded)
• Multirate State Space Models for End-to-End Processing of Pulse Density Modulated Speech Signals#792475arXiv (All)
• AutoConcept: Training-Free Concept-Guided Reranking for Metadata-Available Composed Image Retrieval#821495arXiv (All)
• Stress-Testing DANTE under Detector Domain Shift: a Representation-Coherent Reanalysis of LIGO O4a#628290arXiv (OAI Expanded)
• Stress-Testing DANTE under Detector Domain Shift: a Representation-Coherent Reanalysis of LIGO O4a#630152arXiv (All)
• DANTE: A Reference-Guided Unsupervised Pipeline for Extended-Transient Anomaly Characterization in LIGO O4a#926095arXiv (All)
• Large-Scale Qualitative Research with AI: Infrastructure, Management and Operation of the Socioscope Data Pipeline#796968arXiv (OAI Expanded)
• Large-Scale Qualitative Research with AI: Infrastructure, Management and Operation of the Socioscope Data Pipeline#798381arXiv (All)
• 7 U.S.C. § 1445b-3a — Repealed. Pub. L. 104–127, title I, § 171(b)(2)(D), Apr. 4, 1996, 110 Stat. 938#561750US Code (LII)
• 7 U.S.C. § 1445c-3 — Repealed. Pub. L. 104–127, title I, § 171(b)(2)(E), Apr. 4, 1996, 110 Stat. 938#561755US Code (LII)
• How Developers Discuss Generative AI: A Longitudinal Study of the Visual Studio Code Community#927947arXiv (All)
• Not All Agents Are Equal: Code Quality and Post-Merge Maintenance Across Five Autonomous Coding Agents in the Wild#1011330arXiv (All)
• Single Canonical Prompts Underestimate LLM Safety's Surface-Form Sensitivity#789817arXiv (OAI Expanded)